This repository provides the presentation slides of Computer Vision Study in DAVIAN Lab advised by professor Jaegul Choo.
| Date | Week | Topic | Presenters | Slides |
|---|---|---|---|---|
| 2022.01.03 | Week113 | VA-RED^2 | 정채연 | Slides |
| 2022.01.10 | Week114 | Perceiver | 이관호 | Slides |
| 2022.01.17 | Week115 | PizzaGAN | 조영우 | Slides |
| 2022.01.17 | Week115 | CLIP | 김태우 | Slides |
| 2022.01.24 | Week116 | Florence | 박민호 | Slides |
| 2022.01.24 | Week116 | StyleRig | 박세직 | Slides |
| 2022.02.07 | Week117 | Cross-Domain Weakly Supervised Object Detection | 백서현 | Slides |
| 2022.02.07 | Week117 | BANMo | 김병준 | Slides |
| 2022.02.14 | Week118 | DyHead | 윤희원 | Slides |
| 2022.02.14 | Week118 | TTT++ | 곽대훈 | Slides |
| 2022.02.21 | Week119 | First Order Motion Model | 김기홍 | Slides |
| 2022.02.21 | Week119 | LIA | 이재성 | Slides |
| 2022.03.14 | Week120 | LaMa | 윤주열 | Slides |
| 2022.03.14 | Week120 | CLIP-NeRF | 형준하 | Slides |
| 2022.03.21 | Week121 | The Role of ImageNet Classes in Fréchet Inception Distance | 이상윤 | Slides |
| 2022.03.21 | Week121 | Teachers Do More Than Teach | 정채연 | Slides |
| 2022.03.28 | Week122 | Image and Video Editing with StyleGANv3 | 김태우 | Slides |
| 2022.04.04 | Week123 | INR for Hyperscpectral Imaging | 이한얼 | Slides |
| 2022.04.04 | Week123 | PixMix | 이재성 | Slides |
| 2022.04.11 | Week124 | iMAP | 배광탁 | Slides |
| 2022.04.11 | Week124 | MPViT | 정소희 | Slides |
| 2022.04.18 | Week125 | Hypercon | 박여정 | Slides |
| 2022.04.18 | Week125 | SCNeRF | 김민정 | Slides |
| 2022.04.25 | Week126 | Semantic Image Synthesis | 박민호 | Slides |
| 2022.05.02 | Week127 | NeRFactor | 황성원 | Slides |
| 2022.05.02 | Week127 | UNet Discriminator | 이한얼 | Slides |
| 2022.05.09 | Week128 | HDR Imaging | 윤주열 | Slides |
| 2022.05.09 | Week128 | VolumeGAN | 정윤지 | Slides |
| 2022.05.16 | Week129 | Pik-Fix | 정소희 | Slides |
| 2022.05.16 | Week129 | Weakly Supervised Clothing | 구교정 | Slides |
| 2022.05.23 | Week130 | Backdoor Attacks on SSL | 이재성 | Slides |
| 2022.05.23 | Week130 | MoCoGAN-HD | 정채연 | Slides |
| 2022.05.30 | Week131 | CollaGAN | 이창선 | Slides |
| 2022.06.06 | Week132 | Imagen | 형준하 | Slides |
| 2022.06.06 | Week132 | Your Classifier is an EBM | 이상윤 | Slides |
| 2022.06.13 | Week133 | NeRV | 박여정 | Slides |
| 2022.06.13 | Week133 | Decesion Boundary | 이상현 | Slides |
| 2022.06.20 | Week134 | ROME | 이재성 | Slides |
| 2022.06.20 | Week134 | OCR Survey | 김동현 | Slides |
| 2022.06.27 | Week135 | Latent to Latent | 김상우 | Slides |
| 2022.06.27 | Week135 | SR3 | 남궁영수 | Slides |
-
VA-RED^2: Video Adaptive Redundancy Reduction (정채연)
-
Perceiver: General Perception with Iterative Attention (이관호)
-
How to Make a Pizza: Learning a Compositional Layer-Based GAN Model (조영우)
-
CLIP: Connecting Text and Images (김태우)
-
Florence: A New Foundation Model for Computer Vision (박민호)
-
StyleRig: Rigging StyleGAN for 3D Control over Portrait Images (박세직)
StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
-
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection (백서현)
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection
-
BANMo: Building Animatable 3D Neural Models from Casual Videos (김병준)
BANMo: Building Animatable 3D Neural Models from Casual Videos
-
Dynamic Head: Unifying Object Detection Heads with Attentions (윤희원)
Dynamic Head: Unifying Object Detection Heads with Attentions
-
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? (곽대훈)
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?
-
First Order Motion Model for Image Animation (김기홍)
-
Latent Image Animator: Learning to Animate Images via Latent Space Navigation (이재성)
Latent Image Animator: Learning to Animate Images via Latent Space Navigation
-
LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions (윤주열)
LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions
-
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields (형준하)
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields
-
The Role of ImageNet Classes in Fréchet Inception Distance (이상윤)
-
Teachers Do More Than Teach: Compressing Image-to-Image Models (정채연)
Teachers Do More Than Teach: Compressing Image-to-Image Models
-
Third Time's the Charm? Image and Video Editing with StyleGAN3 (김태우)
Third Time's the Charm? Image and Video Editing with StyleGAN3
-
Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution (이한얼)
Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution
-
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (이재성)
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
-
MPViT: Multi-Path Vision Transformer for Dense Prediction (배광탁)
-
iMAP: Implicit Mapping and Positioning in Real-Time (정소희)
-
HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks (박여정)
HyperCon: Image-To-Video Model Transfer for Video-To-Video Translation Tasks
-
Self-Calibrating Neural Radiance Fields (김민정)
-
Semantic Image Synthesis (박민호)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Semantic Image Synthesis with Spatially-Adaptive Normalization
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
You Only Need Adversarial Supervision for Semantic Image Synthesis
-
NeRFactor (황성원)
NerFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
-
A U-Net Based Discriminator for Generative Adversarial Networks (이한얼)
A U-Net Based Discriminator for Generative Adversarial Networks
-
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline (윤주열)
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
-
3D-aware Image Synthesis via Learning Structural and Textural Representations (정윤지)
3D-aware Image Synthesis via Learning Structural and Textural Representations
-
Pik-Fix: Restoring and Colorizing Old Photos (정소희)
-
Weakly Supervised High-Fidelity Clothing Model Generation (구교정)
-
A Good Image Generator Is What You Need for High-Resolution Video Synthesis (정채연)
A Good Image Generator Is What You Need for High-Resolution Video Synthesis Project Page
-
Backdoor Attacks on Self-Supervised Learning (이재성)
-
CollaGAN: Collaborative GAN for Missing Image Data Imputation (이창선)
CollaGAN: Collaborative GAN for Missing Image Data Imputation
-
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (형준하)
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
-
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One (이상윤)
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
-
NeRV: Neural Representations for Videos (박여정)
-
Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective (이상현)
-
ROME: Realistic one-shot mesh-based head avatars (이재성)
-
Latent to Latent: A Learned Mapper for Identity Preserving Editing of Multiple Face Attributes in StyleGAN-generated Images (김상우)
-
Image Super-Resolution via Iterative Refinement (남궁영수)
-
Morpheus: A Deep Leaning Framework for the Pixel-level Analysis of Astronomical Image Data (황지혜)
-
Advances in Vision Language Pretraining (김동현)
-
Are We Done With ImageNet? (이재성)
-
High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (구교정)
High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions
-
Fast-Vid2Vid (박여정)
Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
-
Advances in Story Visualization (정채연)
- StoryGAN: A Sequential Conditional GAN for Story Visualization, CVPR 2019
- Improved-StoryGAN for sequential images visualization, JVCIR 2020
- (CP-CSV) Character-Preserving Coherent Story Visualization, ECCV 2020
- (DUCO-StoryGAN) Improving Generation and Evaluation of Visual Stories via Semantic Consistency, NAACL 2021
- (VLC-StoryGAN) Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization, EMNLP 2021
- Generating a Temporally Coherent Visual Story with Multimodal Recurrent Transformers, ACL ARR 2022
-
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation (이한얼)
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
-
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions (박민호)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
-
Pretraining is All You Need for Image-to-Image Translation (윤주열)
-
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion (이상윤)
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
-
Few-Shot Head Swapping in the Wild (이재성)
-
Bringing Old Films Back to Life (뭉크소열)